INDEX

Explanations

assertive statements and possibilities related to action or decision-making

oai_token-act-pair · gpt-4o-mini Triggered by @bot

indicates possibility or consequence

np_acts-logits-general · gemini-2.5-flash-lite

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-131k

Configuration

google/gemma-scope-9b-it-res/layer_9/width_131k/average_l0_121

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

Data Type

float32

Hook Name

blocks.9.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

berdayakan

-0.61

EndGlobalSection

-0.57

 AssemblyCompany

-0.56

 unknownFields

-0.54

 AssemblyVersion

-0.52

 pendiente

-0.52

UnsafeEnabled

-0.52

AndEndTag

-0.52

 вікісторінку

-0.51

 iprot

-0.50

POSITIVE LOGITS

 vert

0.45

 mission

0.37

NB

0.36

 mito

0.36

ग्

0.34

NT

0.34

NT

0.33

rd

0.33

Vert

0.32

ObjectMapper

0.32

Activations Density 0.124%

assertive statements and possibilities related to action or decision-making

indicates possibility or consequence

No Comments

No Known Activations